baran 0.1.5 → 0.1.6
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile.lock +1 -1
- data/lib/baran/text_splitter.rb +1 -1
- data/lib/baran/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 3c45d696e127a2bdc00606665d6585c74f0a82657bcce81d3e581fb9d5c3e692
|
|
4
|
+
data.tar.gz: 514c86c899e2a804d26b3bc3f6a24d6d35a8a7108a0450562e3050b3c798a3f0
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 359d335677a6a7c08f31c4f2602915374a4ed09772d045b2d098713e1ae550e81660f762aa6aec8bb3457ef2498a0832e97b26f19b82b7c5a1548fb45b859250
|
|
7
|
+
data.tar.gz: 3a010e8aa5547283641f8069a93e98cb2032a191411ec355398e00b4c83ce0953295c8ffea53e54c9240e2ae6edaa83d330f2d2f84dd3066a48438b9b70b223e
|
data/Gemfile.lock
CHANGED
data/lib/baran/text_splitter.rb
CHANGED
|
@@ -38,7 +38,7 @@ module Baran
|
|
|
38
38
|
if total + split.length >= chunk_size && current_splits.length.positive?
|
|
39
39
|
results << joined(current_splits, separator)
|
|
40
40
|
|
|
41
|
-
while total > chunk_overlap || (total + split.length
|
|
41
|
+
while total > chunk_overlap || (total + split.length >= chunk_size && total.positive?)
|
|
42
42
|
total -= current_splits.first.length
|
|
43
43
|
current_splits.shift
|
|
44
44
|
end
|
data/lib/baran/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: baran
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.1.
|
|
4
|
+
version: 0.1.6
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Moeki Kawakami
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2023-06-
|
|
11
|
+
date: 2023-06-15 00:00:00.000000000 Z
|
|
12
12
|
dependencies: []
|
|
13
13
|
description: Text Splitter for Large Language Model Datasets.
|
|
14
14
|
email:
|